Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 191 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3488. Min Act: -0.0002

Data Index: 968412 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3249. Min Act: -0.0002

Data Index: 1219415 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3224. Min Act: -0.0002

Data Index: 1061953 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3287. Min Act: -0.0002

Data Index: 299057 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2718. Min Act: -0.0002

Data Index: 1307257 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2902. Min Act: -0.0002

Data Index: 1121980 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3066. Min Act: -0.0002

Data Index: 1127879 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2811. Min Act: -0.0002

Data Index: 1078139 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3200. Min Act: -0.0002

Data Index: 466916 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3200. Min Act: -0.0002

Data Index: 373817 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2940. Min Act: -0.0002

Data Index: 54247 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2679. Min Act: -0.0002

Data Index: 835882 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2789. Min Act: -0.0002

Data Index: 24844 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2603. Min Act: -0.0002

Data Index: 453540 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2970. Min Act: -0.0002

Data Index: 309886 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2822. Min Act: -0.0002

Data Index: 339796 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2928. Min Act: -0.0002

Data Index: 1108842 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2787. Min Act: -0.0002

Data Index: 438008 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2633. Min Act: -0.0001

Data Index: 697913 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2830. Min Act: -0.0002

Data Index: 637854 (C4 (Web Text))

Max Activating Token Index: 543